Description
Machine Learning Algorithms in Depth, Video Edition. This course provides engineers with the ability to more effectively troubleshoot and optimize their models by delving into the inner workings and mathematical foundations. Designed for engineers who value a fundamental understanding of algorithm performance, this course provides hands-on explanations of dozens of algorithms. The course focuses on the design principles and theoretical foundations of a wide range of important algorithms, with a particular emphasis on probabilistic methods such as Bayesian inference and deep learning. Key data structures and algorithmic patterns are explored in this course. Each algorithm is taught comprehensively, both from a theoretical and mathematical perspective, and through practical implementations to clearly demonstrate its practical application. The course guides learners from the mathematical foundations of the most basic algorithms to their implementation in Python, demonstrating their applications in areas as diverse as finance, computer vision, and natural language processing. The teaching method is such that each topic is first presented with mathematical extraction and then supplemented with Python coding, clear explanations, and graphical images to provide a complete understanding of how to build and implement models.
What you will learn
- Deep understanding of how algorithms work: Learn how machine learning algorithms work from the ground up to effectively troubleshoot models and improve their performance.
- Explore practical implementations: Explore dozens of ML algorithms, including:
- Monte Carlo Stock Price Simulation
- Image denoising using Mean-Field Variational Inference
- EM algorithm for Hidden Markov Models
- Imbalanced Learning, Active Learning, and Ensemble Learning
- Bayesian Optimization for Hyperparameter Tuning
- Clustering using Dirichlet Process K-Means
- Stock Clusters Based on Inverse Covariance Estimation
- Energy Minimization Using Simulated Annealing
- Image search based on ResNet Convolutional Neural Network
- Anomaly Detection in Time-Series Using Variational Autoencoders
- Mastering the theoretical principles: Understanding the basics of Bayesian inference and deep learning.
- Learn data structures and algorithmic patterns: Familiarize yourself with the core data structures and algorithmic patterns for machine learning.
- Mathematical understanding and implementation: See how each algorithm is mathematically derived and then its practical Python implementation.
This course is suitable for people who:
- Machine Learning Practitioners who are familiar with Linear Algebra, Probability, and Basic Calculus.
- ML engineers who seek a deeper understanding of how algorithms work to troubleshoot and improve model performance.
- Professionals in fields like finance, computer vision, and natural language processing who want to learn related ML algorithms.
- Anyone who wants to comprehensively learn the mathematical foundations and practical implementation of machine learning algorithms.
Course details for Machine Learning Algorithms in Depth, Video Edition
- Publisher: Oreilly
- Instructor: Vadim Smolyakov
- Training level: Beginner to advanced
- Training duration: 6 hours and 21 minutes
Course topics
Course images
Sample course video
Installation Guide
After Extract, view with your favorite player.
Subtitles: None
Quality: 1080p
Download link
Downloadly
Rapidgator link
File(s) password: www.downloadly.ir
File size
1.07 GB
